o h%#@sdZddlmZddlmZmZmZmZddlm Z m Z m Z ddl m Z ddlmZmZddlmZeeZd d iZGd d d e ZGd ddeZdS)z GPT-J model configuration) OrderedDict)AnyListMappingOptional)PreTrainedTokenizer TensorTypeis_torch_available)PretrainedConfig)OnnxConfigWithPast PatchingSpec)loggingzEleutherAI/gpt-j-6BzChttps://huggingface.co/EleutherAI/gpt-j-6B/resolve/main/config.jsoncsVeZdZdZdZdddddZ            dfdd ZZS) GPTJConfiga= This is the configuration class to store the configuration of a [`GPTJModel`]. It is used to instantiate a GPT-J model according to the specified arguments, defining the model architecture. Instantiating a configuration with the defaults will yield a similar configuration to that of the GPT-J [EleutherAI/gpt-j-6B](https://huggingface.co/EleutherAI/gpt-j-6B) architecture. Configuration objects inherit from [`PretrainedConfig`] and can be used to control the model outputs. Read the documentation from [`PretrainedConfig`] for more information. Args: vocab_size (`int`, *optional*, defaults to 50400): Vocabulary size of the GPT-J model. Defines the number of different tokens that can be represented by the `inputs_ids` passed when calling [`GPTJModel`]. n_positions (`int`, *optional*, defaults to 2048): The maximum sequence length that this model might ever be used with. Typically set this to something large just in case (e.g., 512 or 1024 or 2048). n_embd (`int`, *optional*, defaults to 4096): Dimensionality of the embeddings and hidden states. n_layer (`int`, *optional*, defaults to 28): Number of hidden layers in the Transformer encoder. n_head (`int`, *optional*, defaults to 16): Number of attention heads for each attention layer in the Transformer encoder. rotary_dim (`int`, *optional*, defaults to 64): Number of dimensions in the embedding that Rotary Position Embedding is applied to. n_inner (`int`, *optional*, defaults to None): Dimensionality of the inner feed-forward layers. `None` will set it to 4 times n_embd activation_function (`str`, *optional*, defaults to `"gelu_new"`): Activation function, to be selected in the list `["relu", "silu", "gelu", "tanh", "gelu_new"]`. resid_pdrop (`float`, *optional*, defaults to 0.1): The dropout probability for all fully connected layers in the embeddings, encoder, and pooler. embd_pdrop (`int`, *optional*, defaults to 0.1): The dropout ratio for the embeddings. attn_pdrop (`float`, *optional*, defaults to 0.1): The dropout ratio for the attention. layer_norm_epsilon (`float`, *optional*, defaults to 1e-5): The epsilon to use in the layer normalization layers. initializer_range (`float`, *optional*, defaults to 0.02): The standard deviation of the truncated_normal_initializer for initializing all weight matrices. use_cache (`bool`, *optional*, defaults to `True`): Whether or not the model should return the last key/values attentions (not used by all models). Example: ```python >>> from transformers import GPTJModel, GPTJConfig >>> # Initializing a GPT-J 6B configuration >>> configuration = GPTJConfig() >>> # Initializing a model from the configuration >>> model = GPTJModel(configuration) >>> # Accessing the model configuration >>> configuration = model.config ```gptj n_positionsn_embdn_headn_layer)max_position_embeddings hidden_sizenum_attention_headsnum_hidden_layers@Ngelu_newh㈵>{Gz?TPFc s~||_||_||_||_||_||_||_||_| |_| |_ | |_ | |_ | |_ ||_ ||_||_tjd|||d|dS)N) bos_token_id eos_token_idtie_word_embeddings) vocab_sizerrrrn_inner rotary_dimactivation_function resid_pdrop embd_pdrop attn_pdroplayer_norm_epsiloninitializer_range use_cacher$r%super__init__)selfr(rrrrr*r)r+r,r-r.r/r0r1r$r%r&kwargs __class__r'a/var/www/html/ai/venv/lib/python3.10/site-packages/transformers/models/gptj/configuration_gptj.pyr3as* zGPTJConfig.__init__)rrrrrrNrr r r r!r"Tr#r#F)__name__ __module__ __qualname____doc__ model_type attribute_mapr3 __classcell__r'r'r6r8r!s47 rcseZdZ   ddededeedeffdd Ze d e ee e efffd d Z e d e fd dZ e d e fddZ    ddede de dedeed e eeff fdd Ze d e fddZZS)GPTJOnnxConfigdefaultNFconfigtaskpatching_specsuse_pastcs2tj||||dt|jddsd|j_dSdS)N)rCrDrE pad_token_idr)r2r3getattr_configrF)r4rBrCrDrEr6r'r8r3s zGPTJOnnxConfig.__init__returncCsJtddddi}|jr|j|ddddd|d<|Sddd|d<|S) N input_idsbatchsequence)rinputs) directionzpast_sequence + sequenceattention_mask)rrEfill_with_past_key_values_)r4 common_inputsr'r'r8rNszGPTJOnnxConfig.inputscC|jjSN)rHrr4r'r'r8 num_layerszGPTJOnnxConfig.num_layerscCrSrT)rHrrUr'r'r8rrWz"GPTJOnnxConfig.num_attention_heads tokenizer batch_size seq_lengthis_pair frameworkc stt|j|||||d}td|di}|jrItstdddl|dj\}} | d} ||j | |j j |j ffddt |j D|d<|d |d <|jrj|d j} j|d j|| | d gd d |d <|S) N)rZr[r\r]rJzACannot generate dummy past_keys inputs without PyTorch installed.rcs g|] }fqSr')zeros).0_ past_shapetorchr'r8 sz8GPTJOnnxConfig.generate_dummy_inputs..past_key_valuesrP)dtyperM)dim)r2r generate_dummy_inputsrrEr ValueErrorrdshaperrHrrangerVrgcatones) r4rYrZr[r\r]rRordered_inputsrKseqlenpast_key_values_length mask_dtyper6rbr8ris2       z$GPTJOnnxConfig.generate_dummy_inputscCsdS)N r'rUr'r'r8default_onnx_opsetsz!GPTJOnnxConfig.default_onnx_opset)rANF)rXrXFN)r9r:r;r strrr boolr3propertyrintrNrVrrrr rrirtr?r'r'r6r8r@sL   ,r@N)r< collectionsrtypingrrrrrr r configuration_utilsr onnxr r utilsr get_loggerr9logger"GPTJ_PRETRAINED_CONFIG_ARCHIVE_MAPrr@r'r'r'r8s    m